Some questions about ResNet.

[vaynelau]

It is a really nice job! We tried to use resnet as a backbone just like what you did in our own experiment. However, it didn't improve performance as we expected and even performed worse than 4-conv. I wonder if there are some tricks when you trained your model with a resnet. Thank you very much.

[yaoyao-liu]

Hi @laudavid,

Thanks for your interest in our work.

ResNet is proven to be a more efficient backbone for few-shot classification on miniImageNet compared to 4CONV. For the detailed experiment results, please refer to the 16th page of this paper.

If you hope to get more suggestions on ResNet, please provide me with the implementation details and experiment settings.